视野之外即跟踪之外：通过查询状态操纵对基于传播的多目标跟踪器实施对抗攻击
Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
针对 Tracking-by-Query-Propagation 类跟踪器的查询传播机制设计对抗攻击：通过时序查询洪泛耗尽查询预算、通过状态去相关破坏查询更新器的时序记忆，并借助可微传感器欺骗仿真优化扰动，为评估 E2E MOT 跟踪器的鲁棒性提供了可复用的攻击范式与失效模式分析。
原文依据 Temporal Query Flooding: Generates spurious temporally consistent track queries to exhaust the tracker's limited query budget
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，基于查询传播的跟踪（Tracking-by-Query-Propagation，TBP）方法通过支持具备长程时序建模能力的端到端（E2E）流水线，推动了多目标跟踪（MOT）的发展。然而，这种对查询传播的依赖引入了此前未被探索的架构脆弱性，使其易受对抗攻击影响。我们提出 FADE，一个旨在利用这些特定脆弱性的新型攻击框架。FADE 采用两种针对 TBP 核心机制的攻击策略：（i）时序查询洪泛：生成虚假但时序一致的跟踪查询，以耗尽跟踪器有限的查询预算，迫使其终止有效轨迹；（ii）时序记忆破坏：通过状态去相关切断时序链接，并抹除已匹配轨迹所学到的特征身份，从而直接攻击查询更新器的记忆。此外，我们引入一个可微流水线，通过利用先进感知传感器欺骗的仿真来优化这些攻击，使其具备物理世界可实现性。在 MOT17 与 MOT20 基准上的实验表明，FADE 对最优的 TBP 跟踪器极为有效，会造成大量身份切换与轨迹终止。
英文原文摘要 1166 字符
Recent Tracking-by-Query-Propagation (TBP) methods have advanced Multi-Object Tracking (MOT) by enabling end-to-end (E2E) pipelines with long-range temporal modeling. However, this reliance on query propagation introduces unexplored architectural vulnerabilities to adversarial attacks. We present FADE, a novel attack framework designed to exploit these specific vulnerabilities. FADE employs two attack strategies targeting core TBP mechanisms: (i) Temporal Query Flooding: Generates spurious temporally consistent track queries to exhaust the tracker's limited query budget, forcing it to terminate valid tracks. (ii) Temporal Memory Corruption: Directly attacks the query updater's memory by severing temporal links via state de-correlation and erasing the learned feature identity of matched tracks. Furthermore, we introduce a differentiable pipeline to optimize these attacks for physical-world realizability by leveraging simulations of advanced perception sensor spoofing. Experiments on MOT17 and MOT20 benchmarks demonstrate that FADE is highly effective against state-of-the-art TBP trackers, causing significant identity switches and track terminations.